Manufacturing industry-based optimal scheduling method of information system operation and maintenance resources

The idea of ICT-based advanced manufacturing has recently gained prominence due to the fast growth of information and communications technology (ICT). This research proposes a novel technique in optimal scheduling with operation and maintenance system based on data perception and deep learning using multi-objective deterministic gradient schedule optimization. The operation and maintenance have been carried out using data perception-based Bayesian reinforcement transfer learning based on predictive maintenance. The experimental analysis has been carried out based on optimal scheduling and predictive maintenance of the manufacturing industry. The predictive maintenance analysis technique obtained prediction accuracy of 95%, training accuracy 96%, fitness function value 66%, RMSE of 61%, and MAP of 55%, whereas existing PN_GA attained prediction accuracy of 90%, training accuracy 91%, fitness function value 61%, RMSE of 55%, and MAP of 51%; MRO_GA attained prediction accuracy of 92%, training accuracy 93%, fitness function value 65%, RMSE of 58%, and MAP of 53%.